Training in progress, epoch 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5956a0db512d1e58e247a26f38807eb1a78c8355d96596f87ca6d07d3b2621eb
+oid sha256:f3b5ffa34a3adfd4b9c6a5d7f0bbae581eedf0f3df76b82a125760ea6bb19015
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e84d39350bc8fc1f645ab2b411e5ff8b4e453fe06fc4b021854c076780313d
+oid sha256:a525d298ff69c8ddad59af396fca5ee518f3df1b8b4d338e063715105fedc5cf
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2c9985591a0078bc2362c2de2872dd64a7ed4cb1798d0470b0761c289d7ff7
+oid sha256:5304bc487ae5624a2b438d0e3f9f2082f2d01708e1d3ea71c57abc312cf8cdd5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffb0bad2972073c2d12a1b9e761478810ceb0a24e74597b7ad132eee39e244d
+oid sha256:79c112238f59f8e58c9d74f55311cb72b2b120db2461a3e94336debeee3d4c2d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 2952,
+  "global_step": 3280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,13 +154,32 @@
       "eval_samples_per_second": 2.003,
       "eval_steps_per_second": 0.255,
       "step": 2952
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 5.010706638115633e-06,
+      "loss": 0.7252,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 10.529209621993127,
+      "eval_loss": 0.6624875664710999,
+      "eval_rouge1": 34.2518,
+      "eval_rouge2": 25.7147,
+      "eval_rougeL": 30.5433,
+      "eval_rougeLsum": 30.9116,
+      "eval_runtime": 146.9477,
+      "eval_samples_per_second": 1.98,
+      "eval_steps_per_second": 0.252,
+      "step": 3280
     }
   ],
   "logging_steps": 500,
   "max_steps": 3936,
   "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 2.2123279625158656e+16,
+  "total_flos": 2.458142180573184e+16,
   "trial_name": null,
   "trial_params": null
 }